© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 209044
    Prev
    Next
    INDEX
    Explanations

    Create

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    brenner
    0.43
    viewer
    0.42
    smartphone
    0.37
    嬛
    0.37
     smartly
    0.37
    job
    0.36
    smart
    0.35
    teman
    0.35
    }}_{\
    0.35
    inspector
    0.35
    POSITIVE LOGITS
     New
    0.53
     Новый
    0.52
     NEW
    0.47
     নিউ
    0.46
    ческую
    0.45
    만을
    0.44
     LoginForm
    0.44
    New
    0.43
     Нью
    0.43
     நியூ
    0.43
    Activations Density 0.002%

    No Known Activations